Learning to Prune Branches in Modern Tree-Fruit Orchards
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912511473745920 |
|---|---|
| author | Jain, Abhinav Grimm, Cindy Lee, Stefan |
| author_facet | Jain, Abhinav Grimm, Cindy Lee, Stefan |
| contents | Dormant tree pruning is labor-intensive but essential to maintaining modern highly-productive fruit orchards. In this work we present a closed-loop visuomotor controller for robotic pruning. The controller guides the cutter through a cluttered tree environment to reach a specified cut point and ensures the cutters are perpendicular to the branch. We train the controller using a novel orchard simulation that captures the geometric distribution of branches in a target apple orchard configuration. Unlike traditional methods requiring full 3D reconstruction, our controller uses just optical flow images from a wrist-mounted camera. We deploy our learned policy in simulation and the real-world for an example V-Trellis envy tree with zero-shot transfer, achieving a 30% success rate -- approximately half the performance of an oracle planner. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_23015 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning to Prune Branches in Modern Tree-Fruit Orchards Jain, Abhinav Grimm, Cindy Lee, Stefan Robotics Machine Learning Dormant tree pruning is labor-intensive but essential to maintaining modern highly-productive fruit orchards. In this work we present a closed-loop visuomotor controller for robotic pruning. The controller guides the cutter through a cluttered tree environment to reach a specified cut point and ensures the cutters are perpendicular to the branch. We train the controller using a novel orchard simulation that captures the geometric distribution of branches in a target apple orchard configuration. Unlike traditional methods requiring full 3D reconstruction, our controller uses just optical flow images from a wrist-mounted camera. We deploy our learned policy in simulation and the real-world for an example V-Trellis envy tree with zero-shot transfer, achieving a 30% success rate -- approximately half the performance of an oracle planner. |
| title | Learning to Prune Branches in Modern Tree-Fruit Orchards |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2507.23015 |